Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    CWE identifiers and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    containing
    0.57
    ie
    0.57
    sorted
    0.53
    centered
    0.49
     Article
    0.48
    ang
    0.47
    information
    0.47
    ﺩ
    0.47
     qui
    0.46
     Smo
    0.46
    POSITIVE LOGITS
    чиго
    0.64
     mudanças
    0.63
    PAAm
    0.58
     variáveis
    0.58
     macroscopic
    0.57
     polarisation
    0.57
     asteroids
    0.56
     aventuras
    0.56
     buoyancy
    0.54
     bacterias
    0.53
    Act Density 0.001%

    No Known Activations